drm/amdgpu: Update SPM_VMID with the job's vmid when application reserves the vmid
Subsystems (2)
PATCH 1/1 drm/amdgpu: Update SPM_VMID with the job's vmid when application reserves the vmid
SPM access the video memory according to SPM_VMID. It should be updated with the job's vmid right before the job is scheduled. SPM_VMID is a global resource
--- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 4 ++++ 1 file changed, 4 insertions(+)
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +4 -0
@@ -1080,8 +1080,12 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job,struct dma_fence *fence =NULL ;bool pasid_mapping_needed = false;unsigned patch_offset =0 ; +bool update_spm_vmid_needed = (job->vm && (job->vm->reserved_vmid[vmhub] !=NULL ));int r; +if (update_spm_vmid_needed && adev->gfx.rlc.funcs->update_spm_vmid) + adev->gfx.rlc.funcs->update_spm_vmid (adev, job->vmid); +if (amdgpu_vmid_had_gpu_reset (adev, id)) { gds_switch_needed = true; vm_flush_needed = true;
Signature · 6 lines
2.17.1 _______________________________________________ amd-gfx mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/amd-gfx
[AMD Official Use Only - Internal Distribution Only]
Could anyone help to review the patch?
Thanks
Jacob
________________________________
From: He, Jacob <[email protected]>
Sent: Monday, March 2, 2020 1:35:29 PM
To: [email protected] <[email protected]>
Cc: He, Jacob <[email protected]>
Subject: [PATCH] drm/amdgpu: Update SPM_VMID with the job's vmid when application reserves the vmid
SPM access the video memory according to SPM_VMID. It should be updated with the job's vmid right before the job is scheduled. SPM_VMID is a global resource
--- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 4 ++++ 1 file changed, 4 insertions(+)
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +4 -0
@@ -1080,8 +1080,12 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job,struct dma_fence *fence =NULL ;bool pasid_mapping_needed = false;unsigned patch_offset =0 ; +bool update_spm_vmid_needed = (job->vm && (job->vm->reserved_vmid[vmhub] !=NULL ));int r; +if (update_spm_vmid_needed && adev->gfx.rlc.funcs->update_spm_vmid) + adev->gfx.rlc.funcs->update_spm_vmid (adev, job->vmid); +if (amdgpu_vmid_had_gpu_reset (adev, id)) { gds_switch_needed = true; vm_flush_needed = true;
--
2.17.1
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
Am 02.03.20 um 06:35 schrieb Jacob He:
Quoted 15 lines
SPM access the video memory according to
SPM_VMID. It should be updated with the job's vmid right before the job is scheduled.SPM_VMIDis a global resourceChange-Id Id3881908960398f87e7c95026a54ff83ff826700Signed-off-by Jacob He <[email protected]>--- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 4 ++++ 1 file changed, 4 insertions(+)drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +0
-0
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, · line 1088
Quoted 9 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +4
-0@@ -1080,8 +1080,12 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job,struct dma_fence *fence =NULL ;bool pasid_mapping_needed = false;unsigned patch_offset =0 ; +bool update_spm_vmid_needed = (job->vm && (job->vm->reserved_vmid[vmhub] !=NULL ));int r; +if (update_spm_vmid_needed && adev->gfx.rlc.funcs->update_spm_vmid) + adev->gfx.rlc.funcs->update_spm_vmid (adev, job->vmid); +
It would be better if we could do that asynchronously with a register write on the ring.
The alternative is that we block for the VM to be idle in amdgpu_vm_ioctl() before unreserving the VMID.
In other words lock the reservation object of the root PD and call amdgpu_vm_wait_idle() before calling amdgpu_vmid_free_reserved().
Regards,
Christian.
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, · line 1091
Quoted 3 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +0
-0if (amdgpu_vmid_had_gpu_reset (adev, id)) { gds_switch_needed = true; vm_flush_needed = true;
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
[AMD Official Use Only - Internal Distribution Only]
It would be better if we could do that asynchronously with a register write on the ring.
Sorry, I don’t get your point. Could you please elaborate more?
Thanks
Jacob
From: Christian König<mailto:[email protected]>
Sent: Tuesday, March 3, 2020 10:16 PM
To: He, Jacob<mailto:[email protected]>; [email protected]<mailto:[email protected]>
Subject: Re: [PATCH] drm/amdgpu: Update SPM_VMID with the job's vmid when application reserves the vmid
Am 02.03.20 um 06:35 schrieb Jacob He:
Quoted 15 lines
SPM access the video memory according to
SPM_VMID. It should be updated with the job's vmid right before the job is scheduled.SPM_VMIDis a global resourceChange-Id Id3881908960398f87e7c95026a54ff83ff826700Signed-off-by Jacob He <[email protected]>--- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 4 ++++ 1 file changed, 4 insertions(+)drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +0
-0
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, · line 1088
Quoted 9 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +4
-0@@ -1080,8 +1080,12 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job,struct dma_fence *fence =NULL ;bool pasid_mapping_needed = false;unsigned patch_offset =0 ; +bool update_spm_vmid_needed = (job->vm && (job->vm->reserved_vmid[vmhub] !=NULL ));int r; +if (update_spm_vmid_needed && adev->gfx.rlc.funcs->update_spm_vmid) + adev->gfx.rlc.funcs->update_spm_vmid (adev, job->vmid); +
It would be better if we could do that asynchronously with a register write on the ring.
The alternative is that we block for the VM to be idle in amdgpu_vm_ioctl() before unreserving the VMID.
In other words lock the reservation object of the root PD and call amdgpu_vm_wait_idle() before calling amdgpu_vmid_free_reserved().
Regards,
Christian.
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, · line 1091
Quoted 3 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +0
-0if (amdgpu_vmid_had_gpu_reset (adev, id)) { gds_switch_needed = true; vm_flush_needed = true;
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
Christian König
maintainerAm 03.03.20 um 15:34 schrieb He, Jacob:
Quoted 11 lines
[AMD Official Use Only - Internal Distribution Only]
/It would be better if we could do that asynchronously with a register write on the ring.
/
Sorry, I don’t get your point. Could you please elaborate more?
You pass the ring from amdgpu_vm_flush() to the *_update_spm_vmid() functions.
And then instead of using WREG32() you call amdgpu_ring_emit_wreg() to make the write asynchronously on the ring buffer using a CP command.
This way we avoid a bunch of trouble when one process drops the VMID reservation and another one grabs it.
Regards,
Christian.
Quoted 42 lines
Thanks
Jacob
*From: *Christian König <mailto:[email protected]>
*Sent: *Tuesday, March 3, 2020 10:16 PM
*To: *He, Jacob <mailto:[email protected]>; [email protected] <mailto:[email protected]> *Subject: *Re: [PATCH] drm/amdgpu: UpdateSPM_VMIDwith the job's vmid when application reserves the vmidAm 02.03.20 um 06:35 schrieb Jacob He:
Review
Quoted 11 lines
SPM access the video memory according to
SPM_VMID. It should be updated with the job's vmid right before the job is scheduled.SPM_VMIDis a global resourceChange-Id Id3881908960398f87e7c95026a54ff83ff826700Signed-off-by Jacob He <[email protected]>---
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c| 4 ++++1 file changed, 4 insertions(+)(quoted diff) +0
-0
b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.cdrivers/gpu/drm/amd/amdgpu/amdgpu_vm.c int amdgpu_vm_flush(struct amdgpu_ring *ring,
Quoted 4 lines
index
c00696f3017e..c761d3a0b6e8100644drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +0
-0@@ -1080,8 +1080,12 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring,struct
amdgpu_job*job,drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job,
Quoted 4 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +1
-0struct dma_fence *fence = NULL; bool pasid_mapping_needed = false; unsigned patch_offset = 0; + bool update_spm_vmid_needed = (job->vm &&(job->vm->reserved_vmid[vmhub] != NULL));
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c int amdgpu_vm_flush(struct amdgpu_ring *ring, · line 1086
Quoted 3 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +1
-0int r; + if (update_spm_vmid_needed &&
adev->gfx.rlc.funcs->update_spm_vmid)drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, · line 1088
Quoted 2 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +2
-0+ adev->gfx.rlc.funcs->update_spm_vmid (adev, job->vmid); +It would be better if we could do that asynchronously with a register write on the ring.
Quoted 13 lines
The alternative is that we block for the VM to be idle in
amdgpu_vm_ioctl()before unreserving the VMID.In other words lock the reservation object of the root PD and call
amdgpu_vm_wait_idle()before callingamdgpu_vmid_free_reserved().Regards,
Christian.Quoted 3 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +0
-0if (amdgpu_vmid_had_gpu_reset(adev, id)) { gds_switch_needed = true; vm_flush_needed = true;
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
[AMD Official Use Only - Internal Distribution Only]
Thanks! Could you please take an example of trouble “This way we avoid a bunch of trouble when one process drops the VMID reservation and another one grabs it.”?
Thanks
Jacob
From: Koenig, Christian<mailto:[email protected]>
Sent: Tuesday, March 3, 2020 11:03 PM
To: He, Jacob<mailto:[email protected]>; [email protected]<mailto:[email protected]>
Subject: Re: [PATCH] drm/amdgpu: Update SPM_VMID with the job's vmid when application reserves the vmid
Am 03.03.20 um 15:34 schrieb He, Jacob:
[AMD Official Use Only - Internal Distribution Only]
It would be better if we could do that asynchronously with a register write on the ring.
Sorry, I don’t get your point. Could you please elaborate more?
You pass the ring from amdgpu_vm_flush() to the *_update_spm_vmid() functions.
And then instead of using WREG32() you call amdgpu_ring_emit_wreg() to make the write asynchronously on the ring buffer using a CP command.
This way we avoid a bunch of trouble when one process drops the VMID reservation and another one grabs it.
Regards,
Christian.
Thanks
Jacob
From: Christian König<mailto:[email protected]>
Sent: Tuesday, March 3, 2020 10:16 PM
To: He, Jacob<mailto:[email protected]>; [email protected]<mailto:[email protected]>
Subject: Re: [PATCH] drm/amdgpu: Update SPM_VMID with the job's vmid when application reserves the vmid
Am 02.03.20 um 06:35 schrieb Jacob He:
Quoted 15 lines
SPM access the video memory according to
SPM_VMID. It should be updated with the job's vmid right before the job is scheduled.SPM_VMIDis a global resourceChange-Id Id3881908960398f87e7c95026a54ff83ff826700Signed-off-by Jacob He <[email protected]><mailto:[email protected]>--- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 4 ++++ 1 file changed, 4 insertions(+)drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +0
-0
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, · line 1088
Quoted 9 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +4
-0@@ -1080,8 +1080,12 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job,struct dma_fence *fence =NULL ;bool pasid_mapping_needed = false;unsigned patch_offset =0 ; +bool update_spm_vmid_needed = (job->vm && (job->vm->reserved_vmid[vmhub] !=NULL ));int r; +if (update_spm_vmid_needed && adev->gfx.rlc.funcs->update_spm_vmid) + adev->gfx.rlc.funcs->update_spm_vmid (adev, job->vmid); +
It would be better if we could do that asynchronously with a register write on the ring.
The alternative is that we block for the VM to be idle in amdgpu_vm_ioctl() before unreserving the VMID.
In other words lock the reservation object of the root PD and call amdgpu_vm_wait_idle() before calling amdgpu_vmid_free_reserved().
Regards,
Christian.
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, · line 1091
Quoted 3 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +0
-0if (amdgpu_vmid_had_gpu_reset (adev, id)) { gds_switch_needed = true; vm_flush_needed = true;
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
Christian König
maintainerSee the SPM buffer address is set using CP commands as well, right? And those execute asynchronously.
When we now synchronously update the SPM VMID we risk that we switch from one process to another while the new process is not ready yet with its setup.
That could have quite a bunch of unforeseen consequences, including accidentally writing SPM data into the new process address space at whatever buffer address was used before.
This is something we at least should try to avoid.
Regards,
Christian.
Am 03.03.20 um 16:28 schrieb He, Jacob:
Quoted 85 lines
[AMD Official Use Only - Internal Distribution Only]
Thanks! Could you please take an example of trouble “This way we avoid a bunch of trouble when one process drops the VMID reservation and another one grabs it.”?
Thanks
Jacob
*From: *Koenig, Christian <mailto:[email protected]>
*Sent: *Tuesday, March 3, 2020 11:03 PM
*To: *He, Jacob <mailto:[email protected]>; [email protected] <mailto:[email protected]> *Subject: *Re: [PATCH] drm/amdgpu: UpdateSPM_VMIDwith the job's vmid when application reserves the vmidAm 03.03.20 um 15:34 schrieb He, Jacob:
[AMD Official Use Only - Internal Distribution Only]
/It would be better if we could do that asynchronously with a register
write on the ring./Sorry, I don’t get your point. Could you please elaborate more?
You pass the ring from
amdgpu_vm_flush()to the*_update_spm_vmid()functions.And then instead of using
WREG32()you callamdgpu_ring_emit_wreg()to make the write asynchronously on the ring buffer using a CP command.This way we avoid a bunch of trouble when one process drops the VMID reservation and another one grabs it.
Regards,
Christian.Thanks Jacob *From: *Christian König <mailto:[email protected]> *Sent: *Tuesday, March 3, 2020 10:16 PM *To: *He, Jacob <mailto:[email protected]>; [email protected] <mailto:[email protected]> *Subject: *Re: [PATCH] drm/amdgpu: Update SPM_VMID with the job's vmid when application reserves the vmid Am 02.03.20 um 06:35 schrieb Jacob He: > SPM access the video memory according to SPM_VMID. It should be updated > with the job's vmid right before the job is scheduled. SPM_VMID is a > global resource > > Change-Id: Id3881908960398f87e7c95026a54ff83ff826700 > Signed-off-by: Jacob He <[email protected]> <mailto:[email protected]> > --- > drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 4 ++++ > 1 file changed, 4 insertions(+) > > diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c > index c00696f3017e..c761d3a0b6e8 100644 > --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c > +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c > @@ -1080,8 +1080,12 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, > struct dma_fence *fence = NULL; > bool pasid_mapping_needed = false; > unsigned patch_offset = 0; > + bool update_spm_vmid_needed = (job->vm && (job->vm->reserved_vmid[vmhub] != NULL)); > int r; > > + if (update_spm_vmid_needed && adev->gfx.rlc.funcs->update_spm_vmid) > + adev->gfx.rlc.funcs->update_spm_vmid(adev, job->vmid); > + It would be better if we could do that asynchronously with a register write on the ring. The alternative is that we block for the VM to be idle in amdgpu_vm_ioctl() before unreserving the VMID. In other words lock the reservation object of the root PD and call
Quoted 9 lines
amdgpu_vm_wait_idle() before calling amdgpu_vmid_free_reserved().
Regards,
Christian.
> if (amdgpu_vmid_had_gpu_reset(adev, id)) {
> gds_switch_needed = true;
> vm_flush_needed = true;_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
[AMD Official Use Only - Internal Distribution Only]
Oh, you are right! If SPM_VMID is updated by other process while the SPM enabled commands is executing, that will cause VM fault.
Is the wait vm idle right before unreserve vmid still necessary if using asynchroneously setting SPM_VMID?
Thanks
Jacob
From: Koenig, Christian<mailto:[email protected]>
Sent: Tuesday, March 3, 2020 11:36 PM
To: He, Jacob<mailto:[email protected]>; [email protected]<mailto:[email protected]>
Subject: Re: [PATCH] drm/amdgpu: Update SPM_VMID with the job's vmid when application reserves the vmid
See the SPM buffer address is set using CP commands as well, right? And those execute asynchronously.
When we now synchronously update the SPM VMID we risk that we switch from one process to another while the new process is not ready yet with its setup.
That could have quite a bunch of unforeseen consequences, including accidentally writing SPM data into the new process address space at whatever buffer address was used before.
This is something we at least should try to avoid.
Regards,
Christian.
Am 03.03.20 um 16:28 schrieb He, Jacob:
[AMD Official Use Only - Internal Distribution Only]
Thanks! Could you please take an example of trouble “This way we avoid a bunch of trouble when one process drops the VMID reservation and another one grabs it.”?
Thanks
Jacob
From: Koenig, Christian<mailto:[email protected]>
Sent: Tuesday, March 3, 2020 11:03 PM
To: He, Jacob<mailto:[email protected]>; [email protected]<mailto:[email protected]>
Subject: Re: [PATCH] drm/amdgpu: Update SPM_VMID with the job's vmid when application reserves the vmid
Am 03.03.20 um 15:34 schrieb He, Jacob:
[AMD Official Use Only - Internal Distribution Only]
It would be better if we could do that asynchronously with a register write on the ring.
Sorry, I don’t get your point. Could you please elaborate more?
You pass the ring from amdgpu_vm_flush() to the *_update_spm_vmid() functions.
And then instead of using WREG32() you call amdgpu_ring_emit_wreg() to make the write asynchronously on the ring buffer using a CP command.
This way we avoid a bunch of trouble when one process drops the VMID reservation and another one grabs it.
Regards,
Christian.
Thanks
Jacob
From: Christian König<mailto:[email protected]>
Sent: Tuesday, March 3, 2020 10:16 PM
To: He, Jacob<mailto:[email protected]>; [email protected]<mailto:[email protected]>
Subject: Re: [PATCH] drm/amdgpu: Update SPM_VMID with the job's vmid when application reserves the vmid
Am 02.03.20 um 06:35 schrieb Jacob He:
Quoted 15 lines
SPM access the video memory according to
SPM_VMID. It should be updated with the job's vmid right before the job is scheduled.SPM_VMIDis a global resourceChange-Id Id3881908960398f87e7c95026a54ff83ff826700Signed-off-by Jacob He <[email protected]><mailto:[email protected]>--- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 4 ++++ 1 file changed, 4 insertions(+)drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +0
-0
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, · line 1088
Quoted 9 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +4
-0@@ -1080,8 +1080,12 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job,struct dma_fence *fence =NULL ;bool pasid_mapping_needed = false;unsigned patch_offset =0 ; +bool update_spm_vmid_needed = (job->vm && (job->vm->reserved_vmid[vmhub] !=NULL ));int r; +if (update_spm_vmid_needed && adev->gfx.rlc.funcs->update_spm_vmid) + adev->gfx.rlc.funcs->update_spm_vmid (adev, job->vmid); +
It would be better if we could do that asynchronously with a register write on the ring.
The alternative is that we block for the VM to be idle in amdgpu_vm_ioctl() before unreserving the VMID.
In other words lock the reservation object of the root PD and call amdgpu_vm_wait_idle() before calling amdgpu_vmid_free_reserved().
Regards,
Christian.
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, · line 1091
Quoted 3 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +0
-0if (amdgpu_vmid_had_gpu_reset (adev, id)) { gds_switch_needed = true; vm_flush_needed = true;
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
Christian König
maintainerAm 03.03.20 um 17:07 schrieb He, Jacob:
Quoted 8 lines
[AMD Official Use Only - Internal Distribution Only]
Oh, you are right! If
SPM_VMIDis updated by other process while the SPM enabled commands is executing, that will cause VM fault.Is the wait vm idle right before unreserve vmid still necessary if using asynchroneously setting
SPM_VMID?
No, that are alternative approaches.
Updating the VMID asynchronously sounds a bit cleaner to me, but feel free to pick whatever is easier for you to implement.
Regards,
Christian.
Quoted 121 lines
Thanks
Jacob
*From: *Koenig, Christian <mailto:[email protected]>
*Sent: *Tuesday, March 3, 2020 11:36 PM
*To: *He, Jacob <mailto:[email protected]>; [email protected] <mailto:[email protected]> *Subject: *Re: [PATCH] drm/amdgpu: UpdateSPM_VMIDwith the job's vmid when application reserves the vmidSee the SPM buffer address is set using CP commands as well, right? And those execute asynchronously.
When we now synchronously update the SPM VMID we risk that we switch from one process to another while the new process is not ready yet with its setup.
That could have quite a bunch of unforeseen consequences, including accidentally writing SPM data into the new process address space at whatever buffer address was used before.
This is something we at least should try to avoid.
Regards,
Christian.Am 03.03.20 um 16:28 schrieb He, Jacob:
[AMD Official Use Only - Internal Distribution Only]
Thanks! Could you please take an example of trouble “This way we avoid a bunch of trouble when one process drops the VMID reservation and another one grabs it.”?
Thanks
Jacob
*From: *Koenig, Christian <mailto:[email protected]> *Sent: *Tuesday, March 3, 2020 11:03 PM
*To: *He, Jacob <mailto:[email protected]>; [email protected] <mailto:[email protected]> *Subject: *Re: [PATCH] drm/amdgpu: UpdateSPM_VMIDwith the job's vmid when application reserves the vmidAm 03.03.20 um 15:34 schrieb He, Jacob:
[AMD Official Use Only - Internal Distribution Only]
/It would be better if we could do that asynchronously with a register
write on the ring./Sorry, I don’t get your point. Could you please elaborate more?
You pass the ring from
amdgpu_vm_flush()to the*_update_spm_vmid()functions.And then instead of using
WREG32()you callamdgpu_ring_emit_wreg()to make the write asynchronously on the ring buffer using a CP command.This way we avoid a bunch of trouble when one process drops the VMID reservation and another one grabs it.
Regards,
Christian.Thanks
Jacob
*From: *Christian König <mailto:[email protected]> *Sent: *Tuesday, March 3, 2020 10:16 PM
*To: *He, Jacob <mailto:[email protected]>; [email protected] <mailto:[email protected]>
*Subject: *Re: [PATCH] drm/amdgpu: UpdateSPM_VMIDwith the job's vmid when application reserves the vmidAm 02.03.20 um 06:35 schrieb Jacob He:
> SPM access the video memory according toSPM_VMID. It should be updated
> with the job's vmid right before the job is scheduled.SPM_VMIDis a
> global resource
>
> Change-Id: Id3881908960398f87e7c95026a54ff83ff826700 > Signed-off-by: Jacob He <[email protected]> <mailto:[email protected]>
> ---
>drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c| 4 ++++ > 1 file changed, 4 insertions(+)
>
> diff --gita/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.cb/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
> indexc00696f3017e..c761d3a0b6e8100644
> ---a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
> +++b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
> @@ -1080,8 +1080,12 @@ int amdgpu_vm_flush(structamdgpu_ring*ring, structamdgpu_job*job,
> structdma_fence*fence = NULL;
> boolpasid_mapping_needed= false;
> unsignedpatch_offset= 0;
> + boolupdate_spm_vmid_needed= (job->vm&& (job->vm->reserved_vmid[vmhub] != NULL));
> int r;
>
> + if (update_spm_vmid_needed&&adev->gfx.rlc.funcs->update_spm_vmid)
> +adev->gfx.rlc.funcs->update_spm_vmid(adev, job->vmid); > +It would be better if we could do that asynchronously with a register
write on the ring.The alternative is that we block for the VM to be idle in
amdgpu_vm_ioctl()before unreserving the VMID.In other words lock the reservation object of the root PD and call
amdgpu_vm_wait_idle()before callingamdgpu_vmid_free_reserved().
Quoted 7 lines
Regards,
Christian.> if (
amdgpu_vmid_had_gpu_reset(adev, id)) { >gds_switch_needed= true; >vm_flush_needed= true;
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
[AMD Official Use Only - Internal Distribution Only]
Thanks million! I’ll change the patch.
-Jacob
________________________________
From: Koenig, Christian <[email protected]>
Sent: Wednesday, March 4, 2020 12:09:36 AM
To: He, Jacob <[email protected]>; [email protected] <[email protected]>
Subject: Re: [PATCH] drm/amdgpu: Update SPM_VMID with the job's vmid when application reserves the vmid
Am 03.03.20 um 17:07 schrieb He, Jacob:
[AMD Official Use Only - Internal Distribution Only]
Oh, you are right! If SPM_VMID is updated by other process while the SPM enabled commands is executing, that will cause VM fault.
Is the wait vm idle right before unreserve vmid still necessary if using asynchroneously setting SPM_VMID?
No, that are alternative approaches.
Updating the VMID asynchronously sounds a bit cleaner to me, but feel free to pick whatever is easier for you to implement.
Regards,
Christian.
Thanks
Jacob
From: Koenig, Christian<mailto:[email protected]>
Sent: Tuesday, March 3, 2020 11:36 PM
To: He, Jacob<mailto:[email protected]>; [email protected]<mailto:[email protected]>
Subject: Re: [PATCH] drm/amdgpu: Update SPM_VMID with the job's vmid when application reserves the vmid
See the SPM buffer address is set using CP commands as well, right? And those execute asynchronously.
When we now synchronously update the SPM VMID we risk that we switch from one process to another while the new process is not ready yet with its setup.
That could have quite a bunch of unforeseen consequences, including accidentally writing SPM data into the new process address space at whatever buffer address was used before.
This is something we at least should try to avoid.
Regards,
Christian.
Am 03.03.20 um 16:28 schrieb He, Jacob:
[AMD Official Use Only - Internal Distribution Only]
Thanks! Could you please take an example of trouble “This way we avoid a bunch of trouble when one process drops the VMID reservation and another one grabs it.”?
Thanks
Jacob
From: Koenig, Christian<mailto:[email protected]>
Sent: Tuesday, March 3, 2020 11:03 PM
To: He, Jacob<mailto:[email protected]>; [email protected]<mailto:[email protected]>
Subject: Re: [PATCH] drm/amdgpu: Update SPM_VMID with the job's vmid when application reserves the vmid
Am 03.03.20 um 15:34 schrieb He, Jacob:
[AMD Official Use Only - Internal Distribution Only]
It would be better if we could do that asynchronously with a register write on the ring.
Sorry, I don’t get your point. Could you please elaborate more?
You pass the ring from amdgpu_vm_flush() to the *_update_spm_vmid() functions.
And then instead of using WREG32() you call amdgpu_ring_emit_wreg() to make the write asynchronously on the ring buffer using a CP command.
This way we avoid a bunch of trouble when one process drops the VMID reservation and another one grabs it.
Regards,
Christian.
Thanks
Jacob
From: Christian König<mailto:[email protected]>
Sent: Tuesday, March 3, 2020 10:16 PM
To: He, Jacob<mailto:[email protected]>; [email protected]<mailto:[email protected]>
Subject: Re: [PATCH] drm/amdgpu: Update SPM_VMID with the job's vmid when application reserves the vmid
Am 02.03.20 um 06:35 schrieb Jacob He:
Quoted 15 lines
SPM access the video memory according to
SPM_VMID. It should be updated with the job's vmid right before the job is scheduled.SPM_VMIDis a global resourceChange-Id Id3881908960398f87e7c95026a54ff83ff826700Signed-off-by Jacob He <[email protected]><mailto:[email protected]>--- drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 4 ++++ 1 file changed, 4 insertions(+)drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +0
-0
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, · line 1088
Quoted 9 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +4
-0@@ -1080,8 +1080,12 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job,struct dma_fence *fence =NULL ;bool pasid_mapping_needed = false;unsigned patch_offset =0 ; +bool update_spm_vmid_needed = (job->vm && (job->vm->reserved_vmid[vmhub] !=NULL ));int r; +if (update_spm_vmid_needed && adev->gfx.rlc.funcs->update_spm_vmid) + adev->gfx.rlc.funcs->update_spm_vmid (adev, job->vmid); +
It would be better if we could do that asynchronously with a register write on the ring.
The alternative is that we block for the VM to be idle in amdgpu_vm_ioctl() before unreserving the VMID.
In other words lock the reservation object of the root PD and call amdgpu_vm_wait_idle() before calling amdgpu_vmid_free_reserved().
Regards,
Christian.
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, · line 1091
Quoted 3 lines
drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c +0
-0if (amdgpu_vmid_had_gpu_reset (adev, id)) { gds_switch_needed = true; vm_flush_needed = true;
_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx